SilentCipher: Deep Audio Watermarking: Link to arxiv The code is at SilentCipher Repository Code for SilentCipher, a method of embedding watermarking in any audio with state of the art robustness. Currently this repository supports audio at 16kHz and 44.1kHz. Checkout our paper for more details. We have posted some examples from existing watermarking algorithms and how they compare to our watermarking method at EXAMPLES [ arXiv ] [ Colab notebook ] Summary In this paper, we address artefacts introduces by Deep learning based watermarking methods and introduce a way to remove the need for perceptual losses which leads to stable training allowing us to achieve SOTA in terms of both perceptual quality and robustness against distortion. Unlike previous methods which work on 16kHz sampling rate, we also showcase our results on 44.1kHz sampling rates opening the path for practical applications. Abstract In the realm of audio watermarking, it is challenging to simultaneously encode imperceptible messages while enhancing the message capacity and robustness. Although recent advancements in deep learning based methods bolster the message capacity and robustness over traditional methods, the…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy